arXiv AI June 18, 2026 By Le Thien Phuc Nguyen, Zhuoran Yu, Khoa Quang Nhat Cao, Yuwei Guo, Tu Ho Manh Pham, Tuan Tai Nguyen, Toan Ngo Duc Vo, Lucas Poon, Tuan Khai Nguyen, Soochahn Lee, Yong Jae Lee

Revisiting Active Speaker Detection: An In-the-Wild Benchmark for Generalization and Robustness

Read the original on arXiv AI →

arXiv:2505. 21954v2 Announce Type: replace-cross Abstract: We present UniTalk, a novel dataset emphasizing challenging scenarios to enhance model generalization for the task of active speaker detection (ASD).

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

benchmarks

arXiv Computer Vision

Sep 23

ROAM-ASD: Robust Open-World Active Speaker Detection with Flexible Multimodal Fusion

arXiv:2609.26648v1 Announce Type: cross Abstract: Active speaker detection (ASD) requires reliable association between visible faces and acoustic speech, yet existing systems often degrade under chal...

By Pu Wang, Yujun Wang, Hugo Van hamme

multimodal benchmarks

arXiv Computer Vision

Sep 10

AVSRBench: A Multi-Condition AVSR Benchmark

arXiv:2609.10366v1 Announce Type: cross Abstract: While AVSR has achieved sub-1% word error rates on the standard LRS3 benchmark, its reliance on broadcast speech obscures whether this reflects true...

By Rishabh Jain, Naomi Harte

llms fine-tuning multimodal benchmarks

arXiv AI

Jun 3

AVTrack: Audio-Visual Tracking in Human-centric Complex Scenes

arXiv:2606. 02724v1 Announce Type: cross Abstract: Audio-visual speaker tracking aims to localize and track active speakers by leveraging auditory and visual cues, enabling fine-grained, human-centric scene understanding.

By Yaoting Wang, Yun Zhou, Zipei Zhang, Henghui Ding

computer-vision multimodal benchmarks safety

arXiv AI

Jul 10

PS4: Proxy-Supervised Joint Training for Real Target Speaker Extraction

arXiv:2607. 08111v1 Announce Type: cross Abstract: Training target speaker extraction (TSE) models for real conversational mixtures remains challenging because large-scale training corpora and clean target speech for supervision are unavailable.

By Wanyi Ning, Wei Zhou, Yingpeng Li, Yinshang Guo, Haitao Qian, Yiming Cheng

fine-tuning multimodal benchmarks

arXiv Computer Vision

Sep 10

Candor-LR: A Dyadic Conversational Dataset for Audio-Visual Speech Recognition

arXiv:2609.10394v1 Announce Type: cross Abstract: Current audio-visual speech recognition (AVSR) benchmarks, like LRS3, rely heavily on clean, scripted and rehearsed speech. They fail to reflect the...

By Rishabh Jain, Aristeidis Papadopoulos, Zhaofeng Lin, Naomi Harte

multimodal benchmarks

Hugging Face Trending Papers

Sep 1

From Visual Cues to Spoken Narration: Rethinking Audio Description

Audio Description (AD) provides spoken narration of visual events during dialogue gaps, making movies accessible to visually impaired audiences. The problem requires determining both what (which visua...

fine-tuning multimodal benchmarks

One email a morning, machine-written

Related stories

ROAM-ASD: Robust Open-World Active Speaker Detection with Flexible Multimodal Fusion

AVSRBench: A Multi-Condition AVSR Benchmark

AVTrack: Audio-Visual Tracking in Human-centric Complex Scenes

PS4: Proxy-Supervised Joint Training for Real Target Speaker Extraction

Candor-LR: A Dyadic Conversational Dataset for Audio-Visual Speech Recognition

From Visual Cues to Spoken Narration: Rethinking Audio Description